洞察 AI 演进与全球贸易脉动，以全息视野重塑跨域情报流。
Decoding AI evolution and global trade rhythms. High-fidelity intelligence, redefined.
Sound Agentic Science Requires Adversarial Experiments
基于 LLM 的代理正在迅速被用于科学数据分析, 自动化任务，这些任务曾经受到人力时间和专业知识的限制。这个能力是...
LLM-based agents are rapidly being adopted for scientific data analysis, automating tasks once limited by human time and expertise. This capability is...
Memanto: Typed Semantic Memory with Information-Theoretic Retrieval for Long-Horizon Agents
从无状态语言模型推理到持久, 多会话自治代理的转变表明内存是主要架构...
The transition from stateless language model inference to persistent, multi session autonomous agents has revealed memory to be a primary architectura...
Emergent Strategic Reasoning Risks in AI: A Taxonomy-Driven Evaluation Framework
随着推理能力和部署范围同步增长, 大型语言模型 (LLM) 获得了参与服务于自己的行为的能力......
As reasoning capacity and deployment scope grow in tandem, large language models (LLMs) gain the capacity to engage in behaviors that serve their own ...
Self-Correction as Feedback Control: Error Dynamics, Stability Thresholds, and Prompt Interventions in LLMs
迭代式自我修正越来越多地部署在代理 LLM 系统, 中，但重复细化是否会提高或降低性能仍然是一个问题。
Iterative self-correction is increasingly deployed in agentic LLM systems, yet whether repeated refinement improves or degrades performance remains in...
Introducing Background Temperature to Characterise Hidden Randomness in Large Language Models
即使使用温度 $T=0$, 大型语言模型 (LLMs) 进行解码，也可以为相同的输入产生不同的输出。 Thinking Ma 的最新作品...
Even when decoding with temperature $T=0$, large language models (LLMs) can produce divergent outputs for identical inputs. Recent work by Thinking Ma...
CognitiveTwin: Robust Multi-Modal Digital Twins for Predicting Cognitive Decline in Alzheimer's Disease
由于疾病进展的异质性，预测阿尔茨海默的疾病(AD)的个体认知能力下降很困难。可靠的临床...
Predicting individual cognitive decline in Alzheimer's disease (AD) is difficult due to the heterogeneity of disease progression. Reliable clinical to...
AgentSearchBench: A Benchmark for AI Agent Search in the Wild
AI 代理生态系统的快速发展正在改变复杂任务的委派和执行方式,，这为识别合适的任务带来了新的挑战……
The rapid growth of AI agent ecosystems is transforming how complex tasks are delegated and executed, creating a new challenge of identifying suitable...
From Skills to Talent: Organising Heterogeneous Agents as a Real-World Company
通过模块化技能和工具集成，单个代理的能力迅速提高,，但多代理系统仍然受到固定...
Individual agent capabilities have advanced rapidly through modular skills and tool integrations, yet multi-agent systems remain constrained by fixed ...
Superminds Test: Actively Evaluating Collective Intelligence of Agent Society via Probing Agents
集体智慧是指一个群体取得超出任何单个成员单独所能完成的成果的能力。作为大语言...
Collective intelligence refers to the ability of a group to achieve outcomes beyond what any individual member can accomplish alone. As large language...
On the Hybrid Nature of ABPMS Process Frames and its Implications on Automated Process Discovery
任何 AI 增强业务流程管理系统 (ABPMS) 的核心组件是流程框架,，它为系统提供流程意识和定义...
A core component of any AI-Augmented Business Process Management System (ABPMS) is the process frame, which gives the system process-awareness and def...